Papers with a repository link where Syntology ran at least one harvested code sample, whether or not every run was a failure of Syntology's instrument (each stream's ledger splits them). On a card, when the archive marks a repository official for the paper, the Syntology line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded). Each page shows two streams, newest first within each, counted separately: papers newer than the archive snapshot come from Syntology's graph Syntology; the rest are archive rows archive 2025-07-28. The two are never added together.
Newer than the archive snapshot Syntology
Cards 16–30 of 6,651 graph papers newer than 2025-07-28 with a Syntology-ran sample; this feed shows the newest 150, newest arXiv id first. Dates and the abstract sentence are from arXiv's metadata (CC0) for 6,651 of 6,651. Each of the 6,651 has a sample that ran: 5,550 with a run with no instrument failure, 1,101 where every run was a failure of Syntology's instrument.
RoadtoAGI/MUSE14 Sep 2026added by Syntology
LLMs can generate fluent prose.
Syntology
4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 4 of 4 pointer-only
JasonZuu/EHR-Correctness14 Sep 2026added by Syntology
Vision-language models are increasingly explored for clinical prediction from electronic health records and medical images, where identifying unreliable predictions is important for safe deployment.
Syntology
9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 9 of 9 pointer-only
YuMingQian1234/T-LoopFormer14 Sep 2026added by Syntology
Looped Transformers have recently demonstrated strong performance in both reasoning and language tasks by reusing a shared set of parameters across multiple iterations, achieving parameter efficiency without sacrificing…
Syntology
3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
SHH-Han/DNF-SR14 Sep 2026added by Syntology
Benefiting from the powerful generative priors of diffusion models, diffusion-based real-world image super-resolution (Real-ISR) methods have demonstrated impressive performance.To achieve efficient Real-ISR, several…
Syntology
19 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 15 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 21 of 21 pointer-only
PKU-YuanGroup/OpenAI4S14 Sep 2026added by Syntology
AI co-scientists could accelerate computational research, but over a long-running study the workflow also has to stay inspectable, resumable and reproducible, which requires persistent computational state and provenance.
Syntology
14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 4 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 8 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
megagonlabs/absol-bn14 Sep 2026added by Syntology
Large language models are increasingly used as natural-language interfaces to structured data, yet they remain unreliable when answers require consistent evidence conditioning, dependency-aware reasoning, and…
Syntology
7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 13 of 13 pointer-only
ChenZeng001/LiftGCN14 Sep 2026added by Syntology
Finite element stress fields often exhibit strong local non-smoothness, where stress concentrations near holes, notches, and loading regions induce sharp spatial gradients and high-frequency graph components.
Syntology
6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
GaozhanWang/MWZZ-RL-202614 Sep 2026added by Syntology
We study continuous-time and possibly high-dimensional stochastic control problems where drift coefficients and running reward functions are unknown.
Syntology
9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 11 of 11 pointer-only
igeng/HiGFRL14 Sep 2026added by Syntology
Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay between DAG topologies and multi-dimensional resource constraints.
Syntology
1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 1 of 1 pointer-only
LiuTaowen-Tony/agentkv14 Sep 2026added by Syntology
Agentic serving can consume orders of magnitude more tokens than chatbot workloads, stressing both KV-cache capacity and decode-time bandwidth.
Syntology
6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
IQuestLab/ModularRSI14 Sep 2026added by Syntology
Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience.
Syntology
6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
AlignmentResearch/puc13 Sep 2026added by Syntology
The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied.
Syntology
1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 6 of 6 pointer-only
deepsteer/deepsteer13 Sep 2026added by Syntology
Causal claims about large language model (LLM) internals rest on measurements.
Syntology
3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
gyutong406-commits/PC2-AD13 Sep 2026added by Syntology
Low-cost and low-resolution sensors used in edge deployments can produce test point clouds that are substantially sparser than the normal training data.
Syntology
25 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 3 violated, 7 with no contract checked; 13 where Syntology's instrument failed) · 5 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
AltSlate-Labs/jugnu13 Sep 2026added by Syntology
We scale our conventional sub-150M pretraining recipe from 53.5M to 109.7M parameters, holding the method fixed (Qwen3-style decoder with grouped-query attention, RoPE, SwiGLU, RMSNorm, QK-Norm, and a z-loss…
Syntology
3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
From the archive archive 2025-07-28 — filtered to papers Syntology ran Syntology
Cards 16–30 of 38,710 archive papers with a code link, filtered to those where Syntology ran at least one sample (the archive chip labels the rows, the Syntology chip labels the filter; the count is the archive rows that pass it); this feed shows the newest 150, archive date first (newest archive date 2025-07-17). Within a month, dated rows come first, then the 1,274 undated rows placed by the month in their arXiv id. 8 archive papers with neither a date nor an arXiv id cannot be placed and are not listed. Each of the 38,710 has a sample that ran: 31,633 with a run with no instrument failure, 7,077 where every run was a failure of Syntology's instrument.
hicai-zju/kpo officialpytorch15 Jul 2025archive 2025-07-28
Protein language models have emerged as powerful tools for sequence generation, offering substantial advantages in functional optimization and denovo design.
Syntology
official (archive's flag): 2 ran
2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 2 of 2 pointer-only
wumingqi/LLM-Math-Evaluation official14 Jul 2025archive 2025-07-28
The reasoning capabilities of large language models (LLMs) have been a longstanding focus of research.
Syntology
official (archive's flag): 1 ran
1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 1 of 1 pointer-only
sutkarsh/focal officialpytorch14 Jul 2025archive 2025-07-28
Real-world visual perception requires invariance to diverse transformations, yet current methods rely heavily on specialized architectures or training on predefined augmentations, limiting generalization.
Syntology
official (archive's flag): 5 ran
5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
fleecermw/privacyfedllm officialpytorch14 Jul 2025archive 2025-07-28
Large language models (LLMs) typically require fine-tuning for domain-specific tasks, and LoRA offers a computationally efficient approach by training low-rank adapters.
Syntology
official (archive's flag): 3 ran
3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
enyu-liu/disc officialpytorch11 Jul 2025archive 2025-07-28
3D Semantic Scene Completion (SSC) has gained increasing attention due to its pivotal role in 3D perception.
Syntology
official (archive's flag): 7 ran
7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 8 of 8 pointer-only
analokmaus/kaggle-aimo2-fast-math-r1 officialpytorch11 Jul 2025archive 2025-07-28
Enhancing the mathematical reasoning of Large Language Models (LLMs) is a pivotal challenge in advancing AI capabilities.
Syntology
official (archive's flag): 6 ran
6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 6 of 6 pointer-only
hiyouga/easyr1 officialpytorch10 Jul 2025archive 2025-07-28
We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning.
Syntology
official (archive's flag): 4 ran
18 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 1 of 24 pointer-only
soolab/simcis officialpytorch10 Jul 2025archive 2025-07-28
Class-incremental/Continual image segmentation (CIS) aims to train an image segmenter in stages, where the set of available categories differs at each stage.
Syntology
official (archive's flag): 1 ran
1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 1 of 1 pointer-only
svitlana-outsampler/ITS_ICML2025 officialpytorch10 Jul 2025archive 2025-07-28
In this paper, we investigate the distillation of time series reasoning capabilities into small, instruction-tuned language models as a step toward building interpretable time series foundation models.
Syntology
official (archive's flag): 1 ran
1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
cmbagents/cmbagent official9 Jul 2025archive 2025-07-28
We present a multi-agent system for automation of scientific research tasks, cmbagent.
Syntology
official (archive's flag): 1 ran
2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
lain810/dce officialpytorch9 Jul 2025archive 2025-07-28
Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments, requiring models to adjust to evolving domains while preserving historical knowledge.
Syntology
official (archive's flag): 7 ran
7 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 11 of 11 pointer-only
nec-n-sogi/msdpp officialpytorch9 Jul 2025archive 2025-07-28
Result diversification (RD) is a crucial technique in Text-to-Image Retrieval for enhancing the efficiency of a practical application.
Syntology
official (archive's flag): 1 ran
1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
licence: 1 of 1 pointer-only
tyxqc/spindlekv officialpytorch9 Jul 2025archive 2025-07-28
Large Language Models (LLMs) have achieved impressive accomplishments in recent years.
Syntology
official (archive's flag): 7 ran
7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
catherinearnett/morphscore official8 Jul 2025archive 2025-07-28
While tokenization is a key step in language modeling, with effects on model training and performance, it remains unclear how to effectively evaluate tokenizer quality.
Syntology
official (archive's flag): 1 ran
1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
licence: 2 of 2 pointer-only
oppo-personalai/agent-kb official8 Jul 2025archive 2025-07-28
As language agents tackle increasingly complex tasks, they struggle with effective error correction and experience reuse across domains.
Syntology
official (archive's flag): 1 ran
1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
“instrument failed”: failures of Syntology's instrument, not of the code
every run of this paper's code is a failure of Syntology's instrument, not of the code
The feed is static: 10 pages of up to 15 cards per stream, rebuilt with the site. Older papers are reachable from task, dataset and method pages and from search. No repository stars are tracked and nothing here is ranked by popularity. Machine-readable twin: JSON.